{"id":"https://openalex.org/W7165890546","doi":"https://doi.org/10.48550/arxiv.2606.25272","title":"Characterizing Robustness in Semantic Code Clone Detection","display_name":"Characterizing Robustness in Semantic Code Clone Detection","publication_year":2026,"publication_date":"2026-06-24","ids":{"openalex":"https://openalex.org/W7165890546","doi":"https://doi.org/10.48550/arxiv.2606.25272"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2606.25272","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.25272","pdf_url":"https://arxiv.org/pdf/2606.25272","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.25272","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073136550","display_name":"Zhewei Xu","orcid":"https://orcid.org/0000-0003-4718-6175","observed_orcids":["https://orcid.org/0000-0003-4718-6175","https://orcid.org/0009-0007-9440-6552","https://orcid.org/0000-0001-7564-3594","https://orcid.org/0000-0001-8153-1329","https://orcid.org/0000-0002-3117-9934","https://orcid.org/0000-0003-2526-0506","https://orcid.org/0009-0000-4394-5563","https://orcid.org/0009-0002-1114-8783","https://orcid.org/0009-0002-7682-6995","https://orcid.org/0009-0003-9399-5050","https://orcid.org/0009-0004-1711-9953","https://orcid.org/0009-0005-4862-6488","https://orcid.org/0009-0005-9357-5499","https://orcid.org/0009-0006-4012-0885","https://orcid.org/0009-0007-2930-3565","https://orcid.org/0009-0007-6720-0508","https://orcid.org/0009-0008-6580-0259","https://orcid.org/0009-0009-1093-2593","https://orcid.org/0009-0009-4546-6086"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Zhiwei","raw_affiliation_strings":["School of Software , Tsinghua University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software , Tsinghua University , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074616549","display_name":"Weixian Deng","orcid":"https://orcid.org/0000-0003-2597-2255","observed_orcids":["https://orcid.org/0000-0003-2597-2255"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng, Weixian","raw_affiliation_strings":["School of Software , Tsinghua University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software , Tsinghua University , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139348315","display_name":"Xuyang Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Xuyang","raw_affiliation_strings":["School of Software , Tsinghua University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software , Tsinghua University , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139336713","display_name":"Xiaolin Peng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Xiaolin","raw_affiliation_strings":["School of Software , Tsinghua University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software , Tsinghua University , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112625169","display_name":"Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Jiabao","raw_affiliation_strings":["School of Software , Tsinghua University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software , Tsinghua University , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149371090","display_name":"Tian Qiu","orcid":"https://orcid.org/0000-0003-2005-1326","observed_orcids":["https://orcid.org/0000-0003-2005-1326"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiu, Tian","raw_affiliation_strings":["School of Software , Tsinghua University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software , Tsinghua University , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125743175","display_name":"Hai Wan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wan, Hai","raw_affiliation_strings":["School of Software , Tsinghua University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software , Tsinghua University , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100773043","display_name":"Xibin Zhao","orcid":"https://orcid.org/0000-0002-6168-7016","observed_orcids":["https://orcid.org/0000-0002-6168-7016"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Xibin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/program-transformation","display_name":"program transformation","score":0.5389999747276306},{"id":"https://openalex.org/keywords/bigclonebench","display_name":"BigCloneBench","score":0.7670000195503235},{"id":"https://openalex.org/keywords/threshold-recovery","display_name":"threshold recovery","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.758400022983551},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7106000185012817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685699999332428},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6182000041007996},{"id":"https://openalex.org/C37926939","wikidata":"https://www.wikidata.org/wiki/Q7449061","display_name":"Semantic equivalence","level":4,"score":0.5648999810218811},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4860999882221222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47609999775886536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4537999927997589},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3012000024318695},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.26440000534057617}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2606.25272","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.25272","pdf_url":"https://arxiv.org/pdf/2606.25272","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2606.25272","doi":"https://doi.org/10.48550/arxiv.2606.25272","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25272","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.25272","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.25272","pdf_url":"https://arxiv.org/pdf/2606.25272","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7165890546.pdf","grobid_xml":"https://content.openalex.org/works/W7165890546.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W3086007799","https://openalex.org/W3154229486","https://openalex.org/W4322718191","https://openalex.org/W4385967654","https://openalex.org/W4389326242","https://openalex.org/W4416435469"],"related_works":["https://openalex.org/W4396542920","https://openalex.org/W7100361304","https://openalex.org/W4283525684","https://openalex.org/W4313020766","https://openalex.org/W4313563720","https://openalex.org/W4405602123","https://openalex.org/W3202575347","https://openalex.org/W7135388281","https://openalex.org/W2954552517","https://openalex.org/W3175109035"],"abstract_inverted_index":{"Semantic":[0],"code":[1,55,139],"clone":[2],"detection":[3],"seeks":[4],"to":[5,14,18,187,189],"recognize":[6],"shared":[7],"functionality":[8],"across":[9,192],"different":[10,153,174],"implementations,":[11],"making":[12],"robustness":[13],"behavior-preserving":[15],"changes":[16,90],"central":[17],"its":[19],"effectiveness.":[20],"Prior":[21],"studies":[22],"have":[23],"exposed":[24],"failures":[25],"under":[26,116],"such":[27],"changes,":[28],"motivating":[29],"a":[30,49],"systematic":[31,197],"examination":[32],"of":[33,119],"how":[34,196],"sensitivity":[35],"varies":[36],"with":[37,91,125,169],"the":[38,117],"rewrites":[39],"used":[40],"for":[41,176],"evaluation.":[42],"We":[43],"present":[44],"Systematic":[45],"Code":[46,73],"Transformation":[47],"(SCT),":[48],"framework":[50],"organizing":[51],"51":[52],"operators":[53],"by":[54,135],"level,":[56],"target,":[57],"and":[58,61,67,75,83,99,102,128,146,195],"edit":[59,136,147],"category,":[60],"evaluate":[62],"14":[63],"token,":[64,97],"tree,":[65,98],"graph,":[66],"prompt-based":[68],"detectors":[69],"on":[70],"BigCloneBench,":[71],"Google":[72],"Jam,":[74],"OJClone.":[76],"By":[77],"comparing":[78],"transformation":[79,126,198],"groups,":[80],"repeated":[81],"application,":[82],"alternative":[84,149],"constructions,":[85],"we":[86],"connect":[87],"overall":[88],"performance":[89],"specific":[92],"rewriting":[93],"conditions.":[94],"Of":[95],"25":[96],"graph":[100],"detector":[101],"dataset":[103],"combinations":[104],"starting":[105],"above":[106],"90%":[107],"F1,":[108],"21":[109],"lose":[110],"at":[111,143],"least":[112],"10":[113],"percentage":[114],"points":[115],"composition":[118],"all":[120],"operators.":[121],"These":[122],"losses":[123],"vary":[124],"type":[127],"application":[129],"intensity,":[130],"but":[131],"are":[132],"not":[133],"determined":[134],"counts":[137],"or":[138],"growth":[140],"alone.":[141],"Even":[142],"matched":[144],"locations":[145],"counts,":[148],"constructions":[150],"can":[151,200],"expose":[152],"errors":[154],"despite":[155],"similar":[156],"aggregate":[157],"losses.":[158],"Further":[159],"analysis":[160],"distinguishes":[161],"reduced":[162],"score":[163],"separability":[164],"from":[165],"changed":[166],"fixed-threshold":[167],"decisions":[168],"retained":[170],"ranking":[171],"ability,":[172],"revealing":[173],"scope":[175],"threshold":[177],"recovery.":[178],"Overall,":[179],"these":[180],"findings":[181],"show":[182],"why":[183],"benchmark":[184],"effectiveness":[185],"needs":[186],"extend":[188],"stable":[190],"discrimination":[191],"equivalent":[193],"implementations":[194],"testing":[199],"assess":[201],"that":[202],"capability.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-06-26T00:00:00"}